metadata
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Phi-3.5-MultiCap-6
results: []
Phi-3.5-MultiCap-6
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5045
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9384 | 0.2256 | 50 | 0.9431 |
| 0.6189 | 0.4512 | 100 | 0.6235 |
| 0.5667 | 0.6768 | 150 | 0.5738 |
| 0.6109 | 0.9024 | 200 | 0.5533 |
| 0.537 | 1.1280 | 250 | 0.5418 |
| 0.5254 | 1.3536 | 300 | 0.5341 |
| 0.495 | 1.5792 | 350 | 0.5288 |
| 0.5414 | 1.8049 | 400 | 0.5243 |
| 0.5285 | 2.0305 | 450 | 0.5212 |
| 0.4729 | 2.2561 | 500 | 0.5180 |
| 0.5167 | 2.4817 | 550 | 0.5161 |
| 0.5228 | 2.7073 | 600 | 0.5141 |
| 0.5321 | 2.9329 | 650 | 0.5124 |
| 0.5212 | 3.1585 | 700 | 0.5112 |
| 0.5052 | 3.3841 | 750 | 0.5097 |
| 0.4826 | 3.6097 | 800 | 0.5088 |
| 0.5118 | 3.8353 | 850 | 0.5079 |
| 0.4957 | 4.0609 | 900 | 0.5071 |
| 0.4779 | 4.2865 | 950 | 0.5065 |
| 0.4888 | 4.5121 | 1000 | 0.5061 |
| 0.52 | 4.7377 | 1050 | 0.5055 |
| 0.4892 | 4.9633 | 1100 | 0.5052 |
| 0.4881 | 5.1889 | 1150 | 0.5051 |
| 0.5071 | 5.4146 | 1200 | 0.5047 |
| 0.515 | 5.6402 | 1250 | 0.5046 |
| 0.491 | 5.8658 | 1300 | 0.5045 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1